Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to hearing and listening attentively

    oai_token-act-pair · gpt-3.5-turbo

    references to auditory experiences or phrases related to hearing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Athletic
    -0.66
     Regist
    -0.66
     bis
    -0.64
    ucket
    -0.63
    entin
    -0.63
    ulton
    -0.63
    iant
    -0.63
    RGB
    -0.62
     Hilbert
    -0.61
    ritional
    -0.60
    POSITIVE LOGITS
     footsteps
    1.08
     loud
    0.96
     roar
    0.95
     voices
    0.94
     firsthand
    0.88
     louder
    0.87
     podcasts
    0.86
     voice
    0.85
     Voices
    0.82
     noises
    0.81
    Act Density 0.134%

    No Known Activations